CCS论文成果物评估指南

v20260724

ccs-artifact-evaluation

本指南详细介绍了如何在ACM CCS等顶级学术会议上打包和评估论文支持的成果物。它概述了获得不同ACM徽章（如功能性、可重用性、结果可复现性）的标准，确保漏洞利用代码、防御系统和实验数据等支持证据是完整的、可复现的，并为评审委员会提供了详细的文档和操作指南。

CCS 安全成果物评估可复现性学术研究

获取技能

190 次下载

概览

CCS Artifact Evaluation

Use this for artifact packaging around CCS. CCS runs an optional artifact-evaluation process after acceptance; passing artifacts earn ACM badges that appear on the paper's first page. Reopen the current call for artifacts for the exact badge set, submission form, and deadlines.

The ACM badge ladder

Badge	What it certifies	What the committee does
Artifacts Available	The artifact is publicly archived with a stable identifier	Confirms the artifact is retrievable and permanent
Artifacts Evaluated - Functional	The artifact runs and does what the paper says	Executes it against the documented steps
Artifacts Evaluated - Reusable	It exceeds functional quality and others can reuse it	Judges structure, documentation, and reusability
Results Reproduced	The main paper results are independently reproduced	Reruns experiments and checks they support the claims

Available is about archival permanence; Functional and Reusable are about quality; Results Reproduced is the highest bar and requires the committee to regenerate your headline numbers.

Artifact plan

Decide which claims the artifact must support: the exploit, the defense overhead, the measurement pipeline, or the protocol implementation.
Make the security claim turnkey: one documented command per headline result, with expected output, runtime, and the hardware assumed.
Anonymize nothing at this stage — artifact evaluation is post-acceptance and single-blind or open — but do pin versions, dependencies, and a container so it runs on a clean machine.
For dangerous artifacts (working exploits, malware, live attack tooling), gate access, document safe-handling, and follow the responsible-disclosure posture from the paper.
Justify anything withheld: licensing, disclosure embargo, subject safety, or premature-release risk, and offer partial, synthetic, or redacted substitutes that still let evaluators check the method.

What security evaluators open first

Claim type	First artifact inspected	Common failure caught
Exploit against real software	The PoC and its target build instructions	Target version unspecified; PoC fails to build
Defense with overhead numbers	The benchmark runner and instrumented build	Overhead cannot be reproduced; workload undocumented
Measurement study	The collection and classification scripts	Classification rule differs from the paper's prose
Cryptographic implementation	Test vectors and the reference build	No test vectors; outputs cannot be checked

Worked vignette: packaging a fuzzing-tool artifact

A hypothetical accepted paper presents a new fuzzer that found N bugs. For Reusable and Results Reproduced: ship a container pinning the fuzzer, the target corpus, and the seed set; document one command to reproduce a representative crash and one to rerun a bounded campaign; provide the bug list with disclosure status; and note which crashes are embargoed pending vendor patches, offering redacted reproducers for those.

Output format

[Target badges] available / functional / reusable / results-reproduced
[Contents] <code / data / container / test vectors / logs>
[Turnkey level] one-command / scripted / descriptive / weak
[Safe-handling] <gating and disclosure posture for dangerous artifacts>
[Withheld-and-justified] <what and why, with substitute offered>
[Fixes before submission] <ordered list>

信息

Category 硬件工程

Name ccs-artifact-evaluation

版本 v20260724

大小 3.79KB

Source brycewang-stanford/Awesome-Journal-Skills

更新时间 2026-07-28